{"ID":2882589,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.09444","arxiv_id":"2508.09444","title":"DAgger Diffusion Navigation: DAgger Boosted Diffusion Policy for Vision-Language Navigation","abstract":"Vision-Language Navigation in Continuous Environments (VLN-CE) requires agents to follow natural language instructions through free-form 3D spaces. Existing VLN-CE approaches typically use a two-stage waypoint planning framework, where a high-level waypoint predictor generates the navigable waypoints, and then a navigation planner suggests the intermediate goals in the high-level action space. However, this two-stage decomposition framework suffers from: (1) global sub-optimization due to the proxy objective in each stage, and (2) a performance bottleneck caused by the strong reliance on the quality of the first-stage predicted waypoints. To address these limitations, we propose DAgger Diffusion Navigation (DifNav), an end-to-end optimized VLN-CE policy that unifies the traditional two stages, i.e. waypoint generation and planning, into a single diffusion policy. Notably, DifNav employs a conditional diffusion policy to directly model multi-modal action distributions over future actions in continuous navigation space, eliminating the need for a waypoint predictor while enabling the agent to capture multiple possible instruction-following behaviors. To address the issues of compounding error in imitation learning and enhance spatial reasoning in long-horizon navigation tasks, we employ DAgger for online policy training and expert trajectory augmentation, and use the aggregated data to further fine-tune the policy. This approach significantly improves the policy's robustness and its ability to recover from error states. Extensive experiments on benchmark datasets demonstrate that, even without a waypoint predictor, the proposed method substantially outperforms previous state-of-the-art two-stage waypoint-based models in terms of navigation performance. Our code is available at: https://github.com/Tokishx/DifNav.","short_abstract":"Vision-Language Navigation in Continuous Environments (VLN-CE) requires agents to follow natural language instructions through free-form 3D spaces. Existing VLN-CE approaches typically use a two-stage waypoint planning framework, where a high-level waypoint predictor generates the navigable waypoints, and then a naviga...","url_abs":"https://arxiv.org/abs/2508.09444","url_pdf":"https://arxiv.org/pdf/2508.09444v1","authors":"[\"Haoxiang Shi\",\"Xiang Deng\",\"Zaijing Li\",\"Gongwei Chen\",\"Yaowei Wang\",\"Liqiang Nie\"]","published":"2025-08-13T02:51:43Z","proceeding":"cs.RO","tasks":"[\"cs.RO\",\"cs.CV\"]","methods":"[\"Diffusion Model\"]","has_code":false,"code_links":[{"ID":610905,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2882589,"paper_url":"https://arxiv.org/abs/2508.09444","paper_title":"DAgger Diffusion Navigation: DAgger Boosted Diffusion Policy for Vision-Language Navigation","repo_url":"https://github.com/Tokishx/DifNav","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}